© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167878
    Prev
    Next
    INDEX
    Explanations

    to the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unable
    0.45
     thrilled
    0.44
     փ
    0.41
     concerned
    0.40
     सहमत
    0.40
     പിന്നീ
    0.40
     പിന്നീട്
    0.40
     évident
    0.40
    concerned
    0.39
    unable
    0.38
    POSITIVE LOGITS
    ?")
    0.38
     Tet
    0.36
     without
    0.36
     Sig
    0.35
    如果没有
    0.35
    <0xDA>
    0.34
    タウン
    0.34
    )",
    0.33
     કાર્ય
    0.33
    })$,
    0.33
    Activations Density 0.000%

    No Known Activations